Q-Sorting: An Algorithm for Reinforcement Learning Problems with Multiple Cumulative Constraints

Q-Sorting: An Algorithm for Reinforcement Learning Problems with Multiple Cumulative Constraints

This paper proposes a method and an algorithm called Q-sorting for reinforcement learning (RL) problems with multiple cumulative constraints. The primary contribution is a mechanism for dynamically determining the focus of optimization among multiple cumulative constraints and the objective. Execute...

Full description

Bibliographic Details
Main Authors: Jianfeng Huang, Guoqiang Lu, Yi Li, Jiajun Wu
Format: Article
Language:English
Published: MDPI AG 2024-06-01
Series:Mathematics
Subjects:
reinforcement learning
cumulative constraint
constrained Markov decision process (CMDP)
Online Access:https://www.mdpi.com/2227-7390/12/13/2001

Internet

https://www.mdpi.com/2227-7390/12/13/2001

Similar Items